
How to Build a RAG-Powered Chatbot with Chat, Embed, and Rerank
Learn how to build a RAG-powered chatbot with chat, embed, and rerank.

Geospatial generative AI with Amazon Bedrock and Amazon Location Service
Harness the power of geospatial generative AI using Amazon Bedrock and Amazon Location Service to automate geospatial tasks and visualize data

How Amazon Search M5 saved 30% for LLM training cost by using AWS Trainium
How Amazon Search M5 saved 30% for LLM training cost by using AWS Trainium

Build well-architected IDP solutions with a custom lens – Part 5: Cost optimization
Learn how to build cost-optimized intelligent document processing solutions using AWS Well-Architected Framework and best practices.

Build well-architected IDP solutions with a custom lens – Part 4: Performance efficiency
Build well-architected IDP solutions with a custom lens – Part 4: Performance efficiency

Build well-architected IDP solutions with a custom lens – Part 3: Reliability
Build reliable IDP solutions on AWS using well-architected principles.

Build well-architected IDP solutions with a custom lens – Part 2: Security
Learn how to build secure well-architected IDP solutions using a custom lens in AWS, covering security pillars, design principles, access control, data protection, key and secret management, and workload configuration.

Build well-architected IDP solutions with a custom lens – Part 1: Operational excellence
Build well-architected IDP solutions with a custom lens – Part 1: Operational excellence

Build a contextual chatbot for financial services using Amazon SageMaker JumpStart, Llama 2 and Amazon OpenSearch Serverless with Vector Engine
Build a contextual chatbot for financial services using Amazon SageMaker JumpStart, Llama 2 and Amazon OpenSearch Serverless with Vector Engine
Do cats "meow" in every language?
Exploring the fascinating world of animal sound representations in different languages and what it tells us about pronunciation and sound combinations.

Workers AI Update: Hello Mistral 7B
Introducing Mistral 7B, a 7.3 billion parameter language model with grouped-query attention for faster inference and impressive benchmark performance.

Indian Women in Tech: 7 Key Strategies for Elevating Your Salesforce Career
7 key strategies for elevating your Salesforce career as an Indian woman in tech